Abstract: Some embodiments translate express recurrence in natural language into a time stamp for a subsequent recurrence. In these embodiments, a controller receives a trigger and/or a notification for scheduling a next execution date/time from a user interface or a debugger. A GPT schedule may evaluate the natural language from the trigger or natural language from the notification to compute the next execution date/time. Prompt engineering may then be performed to force the GPT scheduler to execute a schedule based on the next execution date/time.

Abstract: A method is provided. The method is executed by a listener service implemented as a computer program executed by a processor. The listener service provides event listeners for change event management. The method includes initiating the event listeners specific to a target application and specifying change events for the event listeners that occur in the target application. The method also includes receiving, by the listener service from the event listeners, the change events in the target application, based on the specified change events, to capture the change events.

Abstract: Access control and governance for automations is disclosed. A code analyzer of an automation designer application, such as a workflow analyzer, may read access control and governance policy rules for an automation designer application and analyze activities of a workflow, tools, and/or prompts of the automation designer application against the access control and governance policy rules. When one or more analyzed activities of the workflow, one or more tools, and/or one or more prompts violate the access control and governance policy rules, the code analyzer prevents generation of an automation robot or publication of the automation until the workflow, the tools, and/or the prompts satisfy the access control and governance policy rules. When the analyzed activities of the workflow, the tools, and or the prompts comply with all required access control and governance policy rules, the automation designer application may generate an automation or publish the automation.

Abstract: Graphical element search technique selection, fuzzy logic selection for anchors and targets, and hierarchical graphical element identification for robotic process automation (RPA) are disclosed. The fuzzy logic selection of anchors and targets may be part of a larger, tiered, or hierarchical process for identifying graphical elements in the UI. When a selector for a UI element is not found with at least a confidence threshold, similar elements potentially corresponding to the selector for a UI element target may be searched based on fuzzy matching of the target and corresponding anchor(s). Geometric matching may also be employed between the target UI element and its respective anchor(s). The combination of fuzzy matching and geometric matching may allow for more flexible and accurate identification of the exact selector with which an RPA robot is attempting to interact.

Abstract: Using agentic artificial intelligence (AI) to supplement automated information extraction, tool selection and use, and/or tool generation is disclosed. AI agents can use tools to extract information (e.g., names, dates, invoice numbers, etc.) from a source. Tools can be selected, used, and/or generated by an AI agent to perform various tasks. Such as the aforementioned information extraction. In other words, an AI agent can run this process, and AI models themselves may be part of the tools. An AI agent can automatically extract information from a screen and generate an agentic loop or some other kind of self-executing loop that can use a screen as an input, for example.

Abstract: Real time bidirectional communication between an automation and a web application is disclosed. In essence, multiple workflows are run. The first is responsible for listening for trigger(s) from a web application. Responsive thereto, this first workflow (e.g., executed by an artificial intelligence (AI) agent or a robotic process automation (RPA) robot) starts execution of a second workflow (e.g., also executed by an AI agent or an RPA robot). The automation also returns a result of the execution of the secondary workflow to the web application.

Abstract: A method is provided. The method is executed by an robotic process automation using a document processing engine. The method includes generate an extracted data prediction of a document by the robotic process automation using multiple distinct document processing operations of the document processing engine. The method includes automatically validating the extracted data prediction by the robotic process automation cross-checking the extracted data prediction with a validator panel of the document processing engine. The method includes determining a confidence for the multiple distinct document processing operations based on the validating of the extracted data prediction.

Abstract: A method is provided. The method is performed by a hyper-automation system performing agentic automations. The hyper-automation system include a memory storing for the agentic automations and for agent health score generation. The hyper-automation system include at least one processor executing the computer code to cause the method to optimize the agentic automations. The method includes generating a set of standardized metrics for application to an agent executing agentic automations. The method includes performing an evaluation of the agent executing the agentic automations that determines performance metrics by measuring success rates, error frequencies, and execution efficiency for different use cases or business processes. The method includes comparing the performance metrics across different use cases or business processes for the agent. The method includes generating agent health scores based on comparing the performance metrics and agent health score definitions.

Abstract: Access control and governance for automations is disclosed. A code analyzer of an automation designer application, such as a workflow analyzer, may read access control and governance policy rules for an automation designer application and analyze activities of a workflow, tools, and/or prompts of the automation designer application against the access control and governance policy rules. When one or more analyzed activities of the workflow, one or more tools, and/or one or more prompts violate the access control and governance policy rules, the code analyzer prevents generation of an automation robot or publication of the automation until the workflow, the tools, and/or the prompts satisfy the access control and governance policy rules. When the analyzed activities of the workflow, the tools, and or the prompts comply with all required access control and governance policy rules, the automation designer application may generate an automation or publish the automation.

Abstract: A method is provided. The method is implemented by a robotic process automation workflow designer application that includes a hypertext transfer protocol recorder feature. The robotic process automation workflow designer application is embodied in software stored on a memory and executed by a processor. The method includes filtering hypertext transfer protocol requests to provide filtered hypertext transfer protocol requests. The method includes recording the filtered hypertext transfer protocol request to provide recorded hypertext transfer protocol requests. The method includes converting the recorded hypertext transfer protocol requests into hypertext transfer protocol request activities. The method includes generating a sequence from the hypertext transfer protocol request activities.

Abstract: Unified artificial intelligence (AI) agent, robotic process automation (RPA) robot, and agentic orchestration process (AOP) development applications are disclosed. In such embodiments, AI agents “coexist” in tandem with RPA robots that execute RPA automations. Automation developers can provide a natural language description of a process intended to be implemented by an AI agent, as well as prompts for a user. Developers can also select grounding context, service integration tools, RPA robots, and escalation attributes for the AI agent. When executed, the AI agent will implement a dynamic flow and attempt to perform its logic autonomously. If this is not successful, the AI agent can escalate to a human-in-the-loop, and the human resolution may be saved in memory for self-healing purposes. Developers can also develop AOPs that can utilize AI agents and RPA robots via a conductor application as well.

Abstract: Unified solutions for agentic automation and robotic process automation (RPA) with self-healing and capabilities to increase autonomy are disclosed. AI agents “coexist” in tandem with RPA robots that execute RPA automations. The AI agents can dynamically leverage the tools available via these RPA robots to perform document processing, user interface (UI) automation, semantic copy-and-paste between a source and a target, etc. AI agents can dynamically select these tools and execute them in the form of a pipeline.

Abstract: Orchestration solutions for agentic automation for artificial intelligence (AI) agents, robotic process automation (RPA) robots, agentic orchestration processes (AOPs), and humans-in-the-loop with self-healing and capabilities to increase autonomy. Agentic orchestration, via a conductor application, enables the automation, modeling, and monitoring of complex business processes from start to finish. A user or an initiating software process requests that a given AOP be run. The AOP defines a business process (e.g., in Business Process Model and Notation (BPMN)), and may utilize one or more RPA robots, one or more AI agents, and/or one or more humans to assist with accomplishing this process, such as resolving invoice discrepancies, onboarding an employee, performing compliance checks, synchronizing order data among multiple backend systems, etc.

Abstract: A method is provided. The method is executed by a document processing and natural language engine implemented as a computer program within a computing environment. The method includes generating parsed non-standardized data from a document or a natural language text and converting the parsed non-standardized data using a generative pretrained transformer into a hypertext markup language output. The method includes extracting pages, controls, or entity fields from the hypertext markup language output using a hypertext markup language application interpreter. The method includes integrating application specific constructs based on the pages, the controls, or the entity fields into an application template to provide an operational form application. The method includes inserting into the operational form application a submit form button configured to push form data to a corresponding entity.

Abstract: A method is disclosed herein. The method includes generating, by the test manager engine utilizing an artificial intelligence model, a textual description of a product or a feature of the product from the first inputs. The method includes receiving, by the test manager engine via a prompt, second inputs in the prompt that alter the textual description to a test description of the product or the feature of the product. The method includes automatically generating, by the test manager engine, test cases for the product or the feature of the product from the test description.

Abstract: A method is provided. The method is executed by a task mining engine implemented as a computer program. The method includes determining, by the task mining engine via a model, similar values of data available from the screen sequence. Each of the similar values are assigned a different key to provide keys. The method includes generating, by the task mining engine, a data structure linking the keys to screens of the screen sequence that each associated similar value appears thereon. The method includes identifying, by the task mining engine via a sequence mining operation, the trace invariants on the screen sequence based on frequently occurring sequences of unique screens associated with each of the keys. The method includes determining, by the task mining engine, a candidate task from the trace invariants.

Abstract: Automation windows for attended or unattended automations are disclosed. A child session is created and hosted as a window including the UIs of applications of a window associated with a parent session. Running multiple sessions allows an automation to operate in this child session while the user or another automation interacts with the parent session. The user or other automation may thus be able to interact with applications that the automation is not using or the user or other automation and the automation may be able to interact with the same application if that application is capable of this functionality. Changes made via the automation and the user or other automation in an application will be made as if a single user made them, rather than having the user or other automation and the automation each work with separate versions of the applications and file systems.

Abstract: An end-to-end automation platform is disclosed that provides a common interface for building applications, data services, and integrations (e.g., processes, queues, entities, connections, etc.). Unified build/project provides a single seamless way of building potentially complex end-to-end automations in certain embodiments, which can be done significantly faster with minimum configuration. The user can build an application in a robotic process automation (RPA) development platform and create workflows in the same interface without leaving the project. The user can leverage the array of activities available in the RPA development platform for handling events in the application, such as button clicks, dropdown value changes, page loads, etc. The user may also build and publish the whole project as a single unit in a conductor application and seamlessly deploy applications along with the attached workflows with a single action.

Abstract: Human-in-the-loop automation training using artificial intelligence (AI) for agentic automation is disclosed. This may be accomplished by a listener watching interactions of a user or an AI agent with a computing system. Based on the interactions by the user or the AI agent with the computing system, the automation may be improved and/or personalized for the user or a group of users.

Abstract: Graphical element search technique selection, fuzzy logic selection for anchors and targets, and hierarchical graphical element identification for robotic process automation (RPA) are disclosed. The fuzzy logic selection of anchors and targets may be part of a larger, tiered, or hierarchical process for identifying graphical elements in the UI. When a selector for a UI element is not found with at least a confidence threshold, similar elements potentially corresponding to the selector for a UI element target may be searched based on fuzzy matching of the target and corresponding anchor(s). Geometric matching may also be employed between the target UI element and its respective anchor(s). The combination of fuzzy matching and geometric matching may allow for more flexible and accurate identification of the exact selector with which an RPA robot is attempting to interact.